The aim of this project is to apply machine learning and signal processing techniques to multiple types of data (electronic health records, electrocardiography, and heart rate variability) to predict heart failure onset, and to use wearable devices to improve the predictions and expand their impact to a wider population. The resulting tools will help prevent delayed diagnosis of heart failure, leading to improved medical outcomes, enhanced patient experience, and reduction in healthcare costs.
Project Number: 1 K01 HL155404-01A1
Name of PD/PI: Ansari, Sardar
Source of Support: NIH/NHLBI
Project Dates: 9/1/2021 – 8/31/2026
Total Award Amount: $817,069
This project aims to build tools that allow for finding patients who suffer from hypertrophic cardiomyopathy. Currently, many patients with this disease are not identified enough for treatment. The study team will use several sources of data that can be used to identify the disease earlier in a federated learning framework in collaboration with AHA and multiple other institutions. This approach protects the patient privacy better than other approaches that are used today. In addition, the study team will explore the implications of using this system in clinics.
Project Number: 24HCMFLP1291285
Name of PD/PI: Ansari, Sardar
Source of Support: American Heart Association
Project Dates: 2/15/2024 – 2/14/2026
Total Award Amount: $498,184
Aim 1: Refine the portable GC device and add VIC detection ability; Aim 2: Using gas chromatography identified breath biomarkers to develop and validate an algorithm based on machine learning and artificial intelligence to detect ARDS and to monitor its trajectory.
Project Number: 1R01HL171517
Name of PD/PI: Fan, Xudong; Sjoding, Michael; Ward, Kevin
Source of Support: NIH
Project Dates: 01/01/2024-12/31/2028
Total Award Amount: $4,169,501
Our main aim is to test a sensor that our team has developed to track artery properties on humans. We will first test whether the sensor measures changes in vessel resistance accurately. We will then test whether sensors can predict major drops in blood pressure before they occur. Finally, we will test the sensors on patients in the hospital.
Project Number: 25CSA1421542
Name of PD/PI: Oldham, Kenn; Ansari, Sardar; Rickards, Caroline; Inyang-Udoh, Uduak
Source of Support: American Heart Association
Project Dates: 4/1/2025-3/31/2028
Total Award Amount: $987,262.00
Many diseases, both internal and cutaneous, have distinct odors associated with them, and their identification can provide unique diagnostic clues, guide laboratory evaluation, and facilitate and expedite treatment. Current body odor analysis relies on benchtop instruments, but they are too bulky for use at point-of-care, home or workplace. E-nose technologies provide a simple, light, and low cost alternative for body odor analysis, but they are highly susceptible to environmental changes (e.g., temperature and humidity).
Project Number: 1-U01-TR-004066-01
Name of PD/PI: Fan, Xudong; Gunnerson, Kyle; Huang, Yvonne; Mahajan, Prashant; Gudjonsson, Johann
Source of Support: NIH
Project Dates: 08/10/2022-05/31/2027
Total Award Amount: $5,505,413
The goal of this project is to reduce patients’ risk of experiencing adverse events during their hospital stay by implementing an early warning system called PICTURE (Predicting Inpatient acute Care Transfers and other UnfoReseen Events). We will design and evaluate an efficient, effective, and user-friendly system interface to deliver PICTURE risk scores and their explanations to providers.
Name of PD/PI: Ansari, Sardar
Project Number: AWD019587
Source of Support: The Doctor’s Company Foundation
Project Dates: 11/1/2021-10/31/2024
Total Award Amount: $100,000
The goal of this project is to prevent inpatient deterioration and adverse events in the pediatric patient population by implementing an early warning system called PICTURE. We will design and evaluate a clinical response that will get triggered when an alert is generated by the model, design an RCT to test the model and the clinical response, and conduct a pilot trial to evaluate the safety and feasibility of the proposed RCT design.
Name of PD/PI: Ansari, Sardar; Daniels, Rodney
Source of Support: The Kahn Pediatric Critical Care Grand Challenge, The Weil Institute for Critical Care Reseach and Innovatoin
Project Dates: 6/1/2024-5/31/2025
Total Award Amount: $99,915
The primary goal of this study is to improve outcomes among patients with acute decompensated heart failure (ADHF) by developing machine-learning-based clinical decision support tools. Specifically, this study seeks to develop and test a reinforcement learning model for treatment recommendations in ADHF.
Name of PD/PI: Admon, Andrew
Source of Support: Cardiovascular Research Network Emerging Investigators Grant Award
Project Dates: 04/01/2025 - 03/31/2029
Total Award Amount: $49,524
Name of PD/PI: Mazumder, Nikhilesh Ray
Source of Support: American College of Gastroenterology
Project Dates: 07/01/2022-06/30/2025
Total Award Amount: $450,000
This study aims to develop and test new computational techniques for acute respiratory distress syndrome (ARDS) detection, incorporating two key factors: (1) training models to account for and note uncertainty and (2) leveraging anatomical information.
Name of PD/PI: Negar Farzaneh
Source of Support: Michigan Institute for Clinical & Health Research (MICHR) K12
Project Dates: 05/01/2022 - 09/30/2025
Total Award Amount: $302,962
Our overall objective is to optimize the care of patients with acute heart and lung diseases by developing data-driven models for precise intensive care unit (ICU) triage and bed assignment. Our overall hypothesis is that personalized triage and bed assignment models can safely reduce rates of clinical deterioration and death among patients with acute heart and lung diseases.
Name of PD/PI: Ansari, Sardar; Admon, Andrew
Source of Support: NIH R01
Project Dates: 04/01/2025 - 03/31/2030
Total Award Amount: $3,847,330
Major Goals: 1. To develop a database of CPR artifact data already collected from commercial defibrillators, and inpatient data. 2. To evaluate and optimize the performance of a model for CPR artifact removal algorithm based on deep learning. 3. To integrate our algorithms into the existing ECG monitoring system at the University of Michigan medical center and evaluate their performance in real time using new CPR data.
Name of PD/PI: Chon, Ki
Source of Support: NIH R01
Project Dates: 04/01/2025 - 03/31/2029
Total Award Amount: $3,371,955
The objectives of this project are (1) to refine an automated, portable, high-performance micro-gas chromatography (GC) device and related data analysis / biomarker identification algorithms for rapid (5-6 minutes), in-situ, and sensitive breath analysis and (2) to conduct breath analysis on up to 760 patients and identify and validate the COVID-19 biomarkers in breath.
Project Number: U18TR003812
Name of PD/PI: Fan, Xudong; Ward, Kevin
Source of Support: NIH
Project Dates: 12/21/2020-11/30/2023
Total Award Amount: $1,942,650
The main objective of this project is to build a tool for real-time monitoring of clinical decision support systems after deployment into the clinical practice to identify when the performance of the system is declining.
Name of PD/PI: Ansari, Sardar
Source of Support: The Michigan Translational Research and Commercialization for Life Sciences
Project Dates: 04/01/2022-06/30/2023
Total Award Amount: $121,563
The goal of this project is to develop a suit of predictive analytics for unexpected patient deterioration on the hospital general wards, as well the tools that enable their deployment.
Name of PD/PI: Ansari, Sardar
Source of Support: Airstrip Technologies, Inc.
Project Dates: 04/01/2022-06/30/2023
Total Award Amount: $1,386,773
The objective of this project is to develop a multi-label classifier that captures (1) the dependency between different output labels as well as (2) the uncertainty about the ground truth labels in the context of electrocardiogram (ECG) classification.
Name of PD/PI: Negar Farzaneh, Hamid Ghanbari
Source of Support: Michigan Institute for Data Science (MIDAS)
Project Dates: 07/30/2022 - 07/29/2023
Total Award Amount: $29,900
The aim of this project is to develop computer vision technologies powered by deep convolutional neural networks to automatically identify chest x-ray findings consistent with ARDS with expert level accuracy. This technology will be a fundamental leap forward for ARDS care and will address a critical limitation in the current diagnosis of ARDS.
Name of PD/PI: Sjoding, Michael
Project Dates: 08/01/2020-01/31/2023
Total Award Amount: $545,326
Name of PD/PI: Admon, Andrew; Gillies, Chris
Source of Support: Michigan Institute for Data Science, University of Michigan
Project Dates: 06/13/2020 – 12/31/2020
Total Award Amount: $30,000
Name of PD/PI: Ansari, Sardar
Project Number: F047228
Source of Support: The Michigan Institute for Clinical & Health Research (MICHR), University of Michigan
Project Dates: 01/06/2017 – 05/30/2019
Total Award Amount: $99,722